{"list":"other","total":61,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"2010.05646","title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","created":"2020-10-12","cited_by_count":1154},{"id":"2301.02111","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","created":"2023-01-05","cited_by_count":752},{"id":"1904.02882","title":"LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech","created":"2019-04-05","cited_by_count":649},{"id":"1908.06112","title":"Symmetric Cross Entropy for Robust Learning with Noisy Labels","created":"2019-08-16","cited_by_count":500},{"id":"1912.07875","title":"Libri-Light: A Benchmark for ASR with Limited or No Supervision","created":"2019-12-17","cited_by_count":467},{"id":"2407.05407","title":"CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens","created":"2024-07-07","cited_by_count":334},{"id":"2412.10117","title":"CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models","created":"2024-12-13","cited_by_count":288},{"id":"2304.09116","title":"NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers","created":"2023-04-18","cited_by_count":235},{"id":"2403.03100","title":"NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models","created":"2024-03-05","cited_by_count":226},{"id":"2407.05361","title":"Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation","created":"2024-07-07","cited_by_count":204},{"id":"2303.03926","title":"Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling","created":"2023-03-07","cited_by_count":167},{"id":"2409.00750","title":"MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer","created":"2024-09-01","cited_by_count":161},{"id":"2105.02446","title":"DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism","created":"2021-05-06","cited_by_count":154},{"id":"2406.05370","title":"VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers","created":"2024-06-08","cited_by_count":122},{"id":"2305.09636","title":"SoundStorm: Efficient Parallel Audio Generation","created":"2023-05-16","cited_by_count":114},{"id":"2010.11567","title":"AISHELL-3: A Multi-speaker Mandarin TTS Corpus and the Baselines","created":"2020-10-22","cited_by_count":111},{"id":"2004.11284","title":"Unsupervised Speech Decomposition via Triple Information Bottleneck","created":"2020-04-23","cited_by_count":88},{"id":"2112.10358","title":"Multi-Singer: Fast Multi-Singer Singing Voice Vocoder With A Large-Scale Corpus","created":"2021-12-20","cited_by_count":60},{"id":"2201.07429","title":"Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis","created":"2022-01-19","cited_by_count":53},{"id":"2305.06908","title":"CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model","created":"2023-05-11","cited_by_count":45},{"id":"2110.08813","title":"VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesis","created":"2021-10-17","cited_by_count":38},{"id":"2406.07855","title":"VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment","created":"2024-06-12","cited_by_count":38},{"id":"2006.06261","title":"XiaoiceSing: A High-Quality and Integrated Singing Voice Synthesis System","created":"2020-06-11","cited_by_count":33},{"id":"2007.04590","title":"DeepSinger: Singing Voice Synthesis with Data Mined From the Web","created":"2020-07-09","cited_by_count":32},{"id":"2203.16705","title":"Robust Disentangled Variational Speech Representation Learning for Zero-shot Voice Conversion","created":"2022-03-30","cited_by_count":28},{"id":"2110.07468","title":"SingGAN: Generative Adversarial Network For High-Fidelity Singing Voice Generation","created":"2021-10-14","cited_by_count":27},{"id":"2305.19269","title":"Make-A-Voice: Unified Voice Synthesis With Discrete Representation","created":"2023-05-30","cited_by_count":27},{"id":"2202.10020","title":"AVQVC: One-shot Voice Conversion by Vector Quantization with applying contrastive learning","created":"2022-02-21","cited_by_count":24},{"id":"2312.10741","title":"StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis","created":"2023-12-17","cited_by_count":21},{"id":"2502.12572","title":"TechSinger: Technique Controllable Multilingual Singing Voice Synthesis via Flow Matching","created":"2025-02-18","cited_by_count":19},{"id":"2305.10763","title":"CLAPSpeech: Learning Prosody from Text Context with Contrastive Language-Audio Pre-training","created":"2023-05-18","cited_by_count":18},{"id":"2108.02776","title":"Sinsy: A Deep Neural Network-Based Singing Voice Synthesis System","created":"2021-08-05","cited_by_count":14},{"id":"2211.02903","title":"VISinger 2: High-Fidelity End-to-End Singing Voice Synthesis Enhanced by Digital Signal Processing Synthesizer","created":"2022-11-05","cited_by_count":14},{"id":"1903.10729","title":"WGANSing: A Multi-Voice Singing Voice Synthesizer Based on the Wasserstein-GAN","created":"2019-03-26","cited_by_count":13},{"id":"2305.10686","title":"RMSSinger: Realistic-Music-Score based Singing Voice Synthesis","created":"2023-05-18","cited_by_count":12},{"id":"2403.11780","title":"Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt","created":"2024-03-18","cited_by_count":12},{"id":"2203.12813","title":"Disentangleing Content and Fine-grained Prosody Information via Hybrid ASR Bottleneck Features for Voice Conversion","created":"2022-03-24","cited_by_count":10},{"id":"2405.09940","title":"Robust Singing Voice Transcription Serves Synthesis","created":"2024-05-16","cited_by_count":10},{"id":"2410.13839","title":"Accelerating Codec-based Speech Synthesis with Multi-Token Prediction and Speculative Decoding","created":"2024-10-17","cited_by_count":10},{"id":"2110.02952","title":"Hierarchical prosody modeling and control in non-autoregressive parallel neural TTS","created":"2021-10-06","cited_by_count":9},{"id":"2306.06814","title":"HiddenSinger: High-Quality Singing Voice Synthesis via Neural Audio Codec and Latent Diffusion Models","created":"2023-06-12","cited_by_count":9},{"id":"2309.00424","title":"Learning Speech Representation From Contrastive Token-Acoustic Pretraining","created":"2023-09-01","cited_by_count":9},{"id":"2309.06787","title":"DCTTS: Discrete Diffusion Model with Contrastive Learning for Text-to-speech Generation","created":"2023-09-13","cited_by_count":9},{"id":"2406.10911","title":"SingMOS: An extensive Open-Source Singing Voice Dataset for MOS Prediction","created":"2024-06-16","cited_by_count":9},{"id":"2107.08248","title":"Learning De-identified Representations of Prosody from Raw Audio","created":"2021-07-17","cited_by_count":8},{"id":"2409.10058","title":"StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion","created":"2024-09-16","cited_by_count":7},{"id":"2406.08416","title":"TokSing: Singing Voice Synthesis based on Discrete Tokens","created":"2024-06-12","cited_by_count":6},{"id":"2501.04256","title":"DrawSpeech: Expressive Speech Synthesis Using Prosodic Sketches as Control Conditions","created":"2025-01-08","cited_by_count":6},{"id":"2505.15402","title":"Prosody-Adaptable Audio Codecs for Zero-Shot Voice Conversion via In-Context Learning","created":"2025-05-21","cited_by_count":6},{"id":"2110.02854","title":"Prosody-TTS: An end-to-end speech synthesis system with prosody control","created":"2021-10-06","cited_by_count":5},{"id":"2412.03388","title":"DiffStyleTTS: Diffusion-based Hierarchical Prosody Modeling for Text-to-Speech with Diverse and Controllable Styles","created":"2024-12-04","cited_by_count":5},{"id":"2202.07907","title":"Singing-Tacotron: Global duration control attention and dynamic filter for End-to-end singing voice synthesis","created":"2022-02-16","cited_by_count":4},{"id":"2501.13870","title":"Everyone-Can-Sing: Zero-Shot Singing Voice Synthesis and Conversion with Speech Reference","created":"2025-01-23","cited_by_count":4},{"id":"2203.17001","title":"SingAug: Data Augmentation for Singing Voice Synthesis with Cycle-consistent Training Strategy","created":"2022-03-31","cited_by_count":3},{"id":"2409.00933","title":"SoCodec: A Semantic-Ordered Multi-Stream Speech Codec for Efficient Language Model Based Text-to-Speech Synthesis","created":"2024-09-02","cited_by_count":3},{"id":"2204.03249","title":"Expressive Singing Synthesis Using Local Style Token and Dual-path Pitch Encoder","created":"2022-04-07","cited_by_count":2}],"next_cursor":null}